# SentencePiece tokenization

Transformer-based bidirectional machine translation model supporting mutual translation among Slavic languages

A sentence similarity model optimized for Russian e-commerce search queries, specifically designed for differentiating product search queries

Arabic-English machine translation model trained on OPUS and HPLT data, available in both Marian and Hugging Face formats.

This is a Transformer-based English to Arabic translation model that supports multiple Arabic dialect variants.

Japanese automatic speech recognition model trained on the ReazonSpeech v2.0 corpus, supporting long audio inference

This is a large-scale Korean automatic speech recognition model based on the Conformer-Transducer architecture, trained on the Ksponspeech dataset, suitable for Korean speech transcription tasks.

This is an English-to-Hebrew machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team as part of the Tatoeba Challenge project.

BERT base model trained on Japanese Wikipedia dataset, suitable for masked language modeling tasks in Japanese text

A Persian language model based on the GPT2 architecture, specifically designed for Persian text generation with enhanced poetry processing capabilities.

This is a Dutch pre-trained model based on the T5 architecture, with 222 million parameters, trained on the cleaned Dutch mC4 dataset.

An English-to-German translation model developed by the Language Technology Research Group at the University of Helsinki, built on the OPUS-MT framework, supporting high-quality machine translation tasks.

This is a Transformer-based multilingual-to-English machine translation model supporting over 100 languages.

This is a Dutch-to-French machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team and trained using the OPUS dataset.

opus-mt-es-de is a Transformer-based machine translation model for Spanish to German, developed by the University of Helsinki NLP team.

A Transformer-based machine translation model from Russian to Ukrainian, developed by the Helsinki-NLP team, supporting standardized preprocessing and SentencePiece tokenization.

A Transformer-based Polish-to-English machine translation model developed by the Helsinki-NLP team, trained using the OPUS dataset.

This is a Transformer-based machine translation model from Spanish to Chinese, supporting multiple Chinese dialects and writing forms.

This is a multilingual translation model based on the Transformer architecture, supporting translation tasks from English to West Slavic languages (including Czech, Polish, etc.).

A Transformer-based Spanish to Polish machine translation model developed by Helsinki-NLP team, trained on the OPUS dataset.

This is a machine translation model based on Transformer architecture for translating from Spanish to Bulgarian, developed by the Helsinki-NLP team.

This is a Bulgarian-to-Turkish machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team.

This is a Finnish-to-Maltese machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team.

This is a machine translation model from Russian to Estonian based on the Transformer architecture, developed by the Helsinki-NLP team as part of the Tatoeba Challenge project.

A Transformer-based machine translation model for Filipino to English, developed by the Helsinki-NLP team, supporting translation from Filipino written in Latin script to English.

This is a Transformer-based machine translation model from English to Vietnamese (including Han character variants), developed by the Helsinki-NLP team.

This is a Bengali-to-English machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team.

This is a Vietnamese-to-Spanish machine translation model based on the transformer-align architecture, developed by the Helsinki-NLP team and released under the Tatoeba-Challenge project.

This is a machine translation model from Ilocano to English based on the transformer-align architecture, developed by the Helsinki-NLP team.

This is a machine translation model based on the Transformer architecture, specifically designed for translation tasks from Cushitic languages (particularly Somali) to English.

This is a machine translation model based on the Transformer architecture, supporting translation tasks from English to various Portuguese-based Creoles and Pidgin languages.

This is a Transformer-based machine translation model from Dutch to Afrikaans, released by the Tatoeba-Challenge project.

This is a Japanese-to-Polish machine translation model based on the transformer-align architecture, developed by the Helsinki-NLP team.

This is a machine translation model based on the Transformer architecture, supporting translation tasks from English to Salishan languages.

This is a Transformer-based machine translation model for English to Ewe, developed by the Helsinki-NLP team.

OPUS-MT German to Italian machine translation model based on Transformer architecture with SentencePiece tokenization

This is a Transformer-based machine translation model for Luganda (lg) to English (en), developed by the Helsinki-NLP team.

This is a machine translation model based on Transformer architecture, specifically designed for translating English into Bulgarian and its Latinized version.

This is a multilingual translation model based on Transformer architecture, supporting translation from various North Germanic languages (including Danish, Norwegian Bokmål, Swedish, etc.) to English.

A Transformer model supporting translation between 136 Indo-European languages, trained by Helsinki-NLP team using OPUS multilingual data

This is a Transformer-based machine translation model from Portuguese to Catalan, developed by the Helsinki-NLP team.